What are the hardware requirements for HY MT1.5 1.8B Bf16?

HY MT1.5 1.8B Bf16 requires approximately 3.6 GB of VRAM and supports a context window of 256K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed HY MT1.5 1.8B Bf16 and how large is it?

HY MT1.5 1.8B Bf16 is developed by mlx-community, a model with 1.8b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate HY MT1.5 1.8B Bf16?

HY MT1.5 1.8B Bf16 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

HY MT1.5 1.8B Bf16 by mlx-community — VRAM 3.6GB, 256K context

Name: HY MT1.5 1.8B Bf16
Author: mlx-community

HY MT1.5 1.8B Bf16 is an open-source language model by mlx-community. Features: 1.8b LLM, VRAM: 3.6GB, Context: 256K, LLM Explorer Score: 0.22.

Ar Base model:finetune:tencent/hy... Base model:tencent/hy-mt1.5-1.... Bn Bo Conversational Cs De En Es Fa Fr Gu He Hi Hunyuan v1 dense Id It Ja Kk Km Ko Mlx Mn Mr Ms My Nl Pl Pt Region:us Ru Safetensors Ta Te Th Tl Tr Translation Ug Uk Ur Vi Zh

Model Card on HF 🤗: https://huggingface.co/mlx-community/HY-MT1.5-1.8B-bf16

HY MT1.5 1.8B Bf16 Parameters and Internals

LLM Name	HY MT1.5 1.8B Bf16
Repository 🤗	https://huggingface.co/mlx-community/HY-MT1.5-1.8B-bf16
Base Model(s)	tencent/HY-MT1.5-1.8B tencent/HY-MT1.5-1.8B
Model Size	1.8b
Required VRAM	3.6 GB
Updated	2026-08-10
Maintainer	mlx-community
Model Type	hunyuan_v1_dense
Model Files	3.6 GB
Supported Languages	zh en fr pt es ja tr ru ar ko th it de vi ms id tl hi pl cs nl km my fa gu ur te mr he bn ta uk bo kk mn ug
Model Architecture	HunYuanDenseV1ForCausalLM
Context Length	262144
Model Max Length	262144
Transformers Version	4.56.1
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<｜hy_▁pad▁｜>
Vocabulary Size	120818

Rank the HY MT1.5 1.8B Bf16 capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to HY MT1.5 1.8B Bf16

Best Alternatives	Context / RAM	Downloads	Likes
Hy MT2 1.8B	256K / 4.1 GB	22767	1131
HY MT1.5 1.8B	256K / 4.1 GB	32205	1184
Hy MT2 1.8B Heretic	256K / 3.6 GB	13	2
Hunyuan 1.8B Instruct	256K / 3.6 GB	272	602
Hunyuan 1.8B Pretrain	256K / 3.6 GB	345	11
HY MT1.5 1.8B 8bit	256K / 1.9 GB	576	5
HY MT1.5 1.8B 4bit	256K / 1 GB	56	3
HY MT1.5 1.8B 6bit	256K / 1.5 GB	10	1
...unyuan 1.8B Instruct GPTQ Int4	256K / 1.3 GB	42	1
Hunyuan 1.8B Instruct AWQ Int4	256K / 1.3 GB	28	3

Note: green Score (e.g. "73.2") means that the model is better than mlx-community/HY-MT1.5-1.8B-bf16.